Horizon Robotics continue to be on a row. It now signed deal to put its J6H chip & HSD 2.0 product on ID. Aura T6 pure electric SUV. Its rapidly going to displace Nvidia in China's ADAS market.

Horizontal expansion reflects the model's strength in semantic juxtaposition and spatial control — laying out multiple concepts within a single image without mutual interference. With just 3.7k tokens, the model renders a 3×3 infographic across 9 domains: tunnel safety comic, spatial geometry, stylistic analysis of Chu Shi Biao, projectile motion, parasitology, chest-pain diagnostics, Sylow theorems, bank internal-control, and DNA structure — every cell precise in text and visuals.

Forza Horizon 6 players in Japan say they’re getting banned over itasha paint jobs. One: “They show absolutely no respect for the culture they used as the game’s main selling point.” Game’s set in Japan. Anime cars are the point. Another: “Some were genuinely against the rules, but the vast majority were just regular itasha paint jobs.” WIP garage drafts and in-game photos of the cars are getting hit too. Players are calling it a mass-report campaign. Hardware bans. Fans say the code of conduct is written “as vague as possible.” Turn 10 updated the Forza rules. Human review. Report count doesn’t change the queue. Playground still hasn’t spoken.

K2 Horizon got another llama.cpp-family path, this time through TurboQuant. Spark-X2.5 already landed in upstream llama.cpp. I’ve actually got it running myself. A brand-new K2 Horizon TurboQuant PR adds … 🧠 K2 Horizon model support 📦 Hugging Face → GGUF conversion 💬 tokenizer + chat templates ⚙️ llama.cpp-style inference And they’ve already tested 🧠 K2-Horizon-3.7B Q4_K_M 🍎 M3 Pro / 18GB ⚡ ~35 tok/s 📚 64K configured context The PR also adds Spark-X2.5 to the TurboQuant fork: ⚡ ~36 tps 📚 256K configured context Caveats ⚠️ This is still an OPEN PR ⚠️ Only Metal has been tested ⚠️ Other K2 sizes + MoVA/MoE variants remain untested K2 Horizon already has an IFM llama.cpp fork, but it still isn’t supported in normal upstream llama.cpp. So what I’m watching here is whether TurboQuant becomes another path for K2.

K2-Horizon-7B scores 21 on Artificial Analysis Intelligence Index, punching above its weights. It scores 50% above the next best model under 10B, beating Qwen3.6-35B-A3B and closely matching Qwen3.6-27B. • Try it: • 8-bit quantization: • Uno, the speed-up diffusion-augmented version:

K2 Horizon is coming to CMU. Following the release, we're hosting a workshop on building with K2 Horizon, followed by an event at HackCMU 2026. We look forward to seeing what CMU's hackers create. Learn more:

Long-horizon RL in the multi-agent context seems to converge to the sort of swarm intelligence seen in ants, not humans. Swarm intelligences are inherently harder to control and monitor.